Basic R

# You can comment your code starting a line with `#`
# 1 + 1
# You have basic operators such as
1 + 1 / 2

1 != 1

(1 + 1) > 3

# You can assign to variables using `<-`, `->`, or `=`
a <- 1234
1 + 1 -> b
c <- "abcd" # Strings can be created using quotes
d <- TRUE

# All of the elements in an atomic vector are only of one type
c(1, 2, 3) # Numeric vector

c(T, F, T) # Logical vector

c("A", "C", "T", "G") # Character vector

# Lists can have different types of items in different components
mylist <- list(1, 2, "A")

vals <- c(1, 2, 5, 1, 2)
c(vals, 13)

max(vals) # Max

which.min(vals) # Argmin

# Random values from a Uniform(a, b)
vals <- runif(n = 100, min = 0, max = 10)
summary(vals)

z_score <- function(x) {
    (x - mean(x, na.rm = TRUE)) / sd(x, na.rm = TRUE)
}

for (j in 1:5) {
    print(j^2)
}

# Install packages from CRAN
install.packages("tidyverse")
# Install packages from Bioconductor
if (!require("BiocManager", quietly = TRUE)) {
    install.packages("BiocManager")
}
BiocManager::install(ggtree)

library(tidyverse)

# Raw data URLs (but it could be local paths also)
uri_adelie <- "https://portal.edirepository.org/nis/dataviewer?packageid=knb-lter-pal.219.3&entityid=002f3893385f710df69eeebe893144ff"
df <- read_csv(uri_adelie)

dim(df) # This shows the dimension of the dataframe

colnames(df) # The names of the columns

glimpse(df) # Quick overview

x <- df[1, ] # Accessing the first row.
x <- df[, 1] # Accessing the first column.
df[, "studyName"] # Accessing the column by name

df[1, "Species"] # Accessing the first row of the column "Species"

c(1, 2, NA, 5) %>%
    sum() %>%
    as.character()

c(1, 2, NA, 5) %>%
    sum(na.rm = T) %>%
    as.character()

df %>%
    mutate(Sex = tolower(Sex)) %>%
    filter(Sex == "female") %>%
    filter(Island %in% c("Torgersen", "Biscoe", "Dream")) %>%
    filter(!is.na(Stage)) %>%
    select("Island", starts_with("Culmen")) %>%
    slice_sample(n = 5)

df2 <- df %>%
    # mutate() is used to create columns
    mutate(Sex = tolower(Sex)) %>%
    # filter() by column Value
    filter(Sex == "female") %>%
    # filter() by list of values
    filter(Island %in% c("Torgersen", "Biscoe", "Dream")) %>%
    # filter() by missing values
    filter(!is.na(Stage)) %>%
    # select() certain columns by index, name or pattern
    select("Island", starts_with("Culmen")) %>%
    # Take a random sample of rows
    slice_sample(n = 5)

cols <- c("Culmen Length (mm)", "Flipper Length (mm)", "Body Mass (g)")
plot(df[, cols])

hist(df[["Culmen Length (mm)"]],
    main = "Distribution of Culmen Length",
    xlab = "Culmen Length (mm)",
    col = "skyblue",
    border = "black",
)

# Set a theme
theme_set(ggthemes::theme_tufte())
df %>%
    # Discard individuals with unknown sex
    filter(!is.na(Sex)) %>%
    # Create a plot with Body mass in the x-axis and fill by Sex
    ggplot(aes(x = `Body Mass (g)`, fill = Sex)) +
    # Plot an histogram
    geom_histogram(color = "black", alpha = 0.8) +
    xlab("Count") + # X-axis label
    ggtitle("Histogram example") # Add title

df %>%
    filter(!is.na(Sex)) %>%
    ggplot(aes(x = `Flipper Length (mm)`, y = `Body Mass (g)`, colour = Sex)) +
    geom_smooth(method = lm, linetype = "dashed") +
    geom_point(shape = 1) +
    facet_wrap(~Island) +
    ggtitle(
        label = "Flipper Length versus Body Mass",
        subtitle = "We don't see differences between islands but between sexes in Adelie Penguin"
    )